© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 33910
    Prev
    Next
    INDEX
    Explanations

    specific formal vocabulary

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     magnético
    -1.02
     volantes
    -0.98
     burbujas
    -0.92
     veces
    -0.90
    cuencia
    -0.89
     fabricado
    -0.88
    ionario
    -0.85
    יים
    -0.85
    Kirch
    -0.84
    nessy
    -0.84
    POSITIVE LOGITS
    ؟؟
    1.02
     عسل
    1.02
     fervent
    1.02
    人たち
    1.00
     gewisse
    0.99
     طلا
    0.98
     molti
    0.98
     alcuni
    0.96
     giacca
    0.96
    ":"",
    0.95
    Activations Density 0.128%

    No Known Activations